Skip to search boxSkip to navigationSkip to main content

An encoder-decoder architecture with graph convolutional networks for abstractive summarization

  • Gangmin Li
    ,
  • QiAo Yuan
    ,
  • Pin Ni
    ,
  • Junru Liu
    ,
  • Xiangzhi Tong
    ,
  • Hanzhe Lu
  • The University of Auckland
    ,
  • Xi'an Jiaotong-Liverpool University
Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Open access

Abstract

We propose a single-document abstractive summarization system that integrates token relation into a traditional RNN-based encoder-decoder architecture. We employ pointer-wise mutual information to represent the token relation and adopt Graph Convolutional Networks (GCN) to extract token representation from the relation graph. In our experiment on Gigaword, we consider importing two kinds of structural information: token (node) representation from the relation graph. Also, we implement two kinds of GCNs, a spectral-based one and a spatial-based one, to extract structural information. The result shows that the spatial based GCN-enhanced model with node representation outperforms the classical RNN-based encoder-decoder model.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 91-97 (7 pages)

Publication milestones

  • Published - 20/08/2021

Publication status

Published - 20/08/2021

Publisher

Institute of Electrical and Electronics Engineers Inc., United States

Publication series

  • Publication series name: 2021 IEEE 4th International Conference on Big Data and Artificial Intelligence, BDAI 2021

ISBN (Print)

9781665412704

ISBN (Electronic)

9781665412704

Publication IDs

  • handle.net: 10547/625922
  • Scopus: 85114508802

Host publication title

2021 IEEE 4th International Conference on Big Data and Artificial Intelligence, BDAI 2021

Access to documents

Publication metrics

Metrics

Download statistics
Download count
3